© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 350
    Prev
    Next
    INDEX
    Explanations

    social media handles on Twitter

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    373
    +0.10
    0.5%
    613
    +0.10
    0.5%
    396
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.10
    0.04
    613
    +0.10
    0.04
    508
    +0.09
    0.04
    Negative Logits
    vernment
    -0.67
    pread
    -0.63
    gery
    -0.63
     999
    -0.60
    ometric
    -0.59
     recomp
    -0.58
    geries
    -0.58
     plurality
    -0.57
     Hebdo
    -0.57
     compromises
    -0.55
    POSITIVE LOGITS
    Newsletter
    0.77
     (@
    0.76
    Subscribe
    0.73
    <|endoftext|>
    0.72
     HERE
    0.71
    edin
    0.68
    Follow
    0.66
     @
    0.66
     Beh
    0.63
     Follow
    0.62
    Activations Density 0.117%

    No Known Activations